inferstep/ATLAS
Adaptive Test-time Learning and Autonomous Specialization
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
4 releases in the last 90 days, the latest 2 days ago, with 10 contributors on GitHub.
Gained 46% fewer stars in the last 90 days than in the 90 days before.
Use Cases & Benefits
- Provides a fully self-hosted AI coding assistant using local frozen models with constraint-driven generation and self-verified repair without cloud dependencies.
- Enables reliable, privacy-preserving code generation and verification on consumer GPUs without requiring fine-tuning or expensive cloud APIs.
- Use for developing secure, offline AI coding tools that run entirely on local hardware with no external API calls.
- Use for integrating multi-language code generation and sandboxed test execution in developer workflows requiring high reliability.
- Use for researchers building adaptive test-time learning systems with energy-based verification and grammar-constrained inference.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
AGPL 3.0
Network copyleft: like the GPL, and also triggered by offering the software over a network.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
- AGPL-style copyleft also applies when the software is offered over a network.
General guidance from repository metadata, not legal advice. How we score
From the README
Adaptive Test-time Learning and Autonomous Specialization
ATLAS is a fully self-hosted coding assistant powered by intelligent inference infrastructure. We wrap a frozen local model in constraint-driven generation, energy-based verification, and self-verified repair - no fine-tuning, no API calls, no cloud. ATLAS exists to prove that meaningful AI tooling doesn't require frontier models, cloud APIs, or massive budgets - just smart infrastructure around capable open-weight models.
Full documentation - setup guides, architecture, configuration, troubleshooting, and benchmark reports - lives in the docs/ directory.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
201+17
Open issues
109+92
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| anthropics/skills | 187.8K | +2.9K | 15 | — |
| DuarteSantos8/openGym | 19.7K | +2.4K | 60 | 2 days ago |
| shiyu-coder/Kronos | 47.0K | +2.3K | 16 | — |
| NationalSecurityAgency/ghidra | 98.2K | +2.3K | 64 | 14 days ago |
| microsoft/VibeVoice | 56.0K | +1.1K | 29 | — |
| inferstep/ATLAS | 2.1K | — | 47 | 2 days ago |
| Category median | 56.0K | +2.3K | 29 | — |
Discover Repositories
Search across tracked repositories by name or description